About
I am an AI/ML Engineer with 4+ years of experience building production-grade machine learning systems across healthcare imaging and financial services. I specialize in the full ML lifecycle — from data engineering and model development to cloud deployment and real-time monitoring. At Philips Healthcare, I lead computer vision pipelines that process over 10,000 chest X-rays daily, achieving 92% anomaly-detection precision, and integrate LLMs to automate radiology report generation. At HDFC Bank, I built NLP-driven fraud detection systems that analyzed over 5 million daily transactions with 95% recall — helping protect customers at scale. I'm experienced across a broad stack, including PyTorch, TensorFlow, Hugging Face Transformers, LangChain, AWS SageMaker, Azure ML, and Kubernetes, with a strong focus on MLOps practices like CI/CD automation, federated learning, and model explainability. I'm passionate about building AI systems that don't just perform in research settings, but solve real problems in production — reliably, responsibly, and at scale.
Professional Experience
AI/ML Engineer
Philips Healthcare -- Orlando, FL
Dec 2024 -- Present
- --Built end-to-end computer vision models using PyTorch and OpenCV to process 10,000+ chest X-
- --rays daily, achieving 92% anomaly detection precision. Deployed on AWS SageMaker with
- --hyperparameter tuning via Weights & Biases, cutting training time by 40%.
- --Designed and fine-tuned CNN architectures (ResNet, YOLOv8) for lung disease detection, achieving
- --a 28% accuracy improvement on internal benchmarks. Integrated inference serving through
- --Kubernetes across clinical environments.
- --Built real-time inference APIs using FastAPI with TensorRT optimization, bringing latency down
- --from 2 seconds to 150ms on edge devices used by radiologists.
- --Implemented federated learning using the Flower framework to train models across 5 hospital sites
- --without centralizing patient data, maintaining HIPAA compliance and improving generalization by
- --15%.
- --Integrated BERT-based LLMs (Hugging Face) for automated generation of radiology reports from
- --image analysis results, reducing radiologist review time by approximately 35%.
- --Automated CI/CD pipelines with Docker, Jenkins, and GitHub Actions, compressing quarterly model
- --release cycles from 4 weeks down to 1 week. Managed versioning of 20+ model artifacts in MLflow.
AI/ML Engineer
HDFC Bank -- Bengaluru, India
Dec 2019 -- Nov 2022
- --Led NLP pipeline development for real-time transaction fraud detection using Hugging Face
- --Transformers and TensorFlow. System processed 5M+ daily transactions on Azure ML, achieving
- --95% recall with a 30% reduction in false positives.
- --Built LSTM and Transformer models for time-series risk forecasting, incorporating Graph Neural
- --Networks (PyTorch Geometric) to identify fraud ring patterns at 85% accuracy. Scaled ingestion
- --through Kafka for high-velocity streaming.
- --Applied SMOTE oversampling to 1M+ labeled transaction records via Dask and spaCy, improving
- --model F1-score by 22%. Tuned XGBoost and LightGBM models for credit risk scoring, gaining an
- --18% AUC-ROC improvement.
- --Developed SHAP and LIME explainability layers to produce compliance reports that satisfied RBI
- --audit requirements and reduced fraud investigation times by 40%.
- --Automated weekly model retraining workflows with MLflow and Airflow to handle data drift,
- --maintaining 99.9% uptime during peak hours across 50TB+ of historical data in Hadoop.
Skills
Education
Master of Science | Information Systems Management
Marist College -- Poughkeepsie, NY
Jan 2023 -- Dec 2024
Bachelor of Technology | Mechanical Engineering
SIR C.R.R. College of Engineering -- Eluru, India